Error Back-Propagation in Multi-valued Logic Systems
Georgios Apostolikas, Stasinos Konstantopoulos · 2007
Error back-propagation - and its many variations - has been used extensively to train neural networks. A multi-layer system cannot be trained in a supervised learning scheme because data are usually provided only as end-to-end input-output pairs for the global system. The central idea of error back-propagation is to derive target input-output pairs for each layer in the system from the global input-output data. We propose a new method for error-back propagation in a fuzzy description logic reasoning system. This permits us to derive input-output data pairs in a two-layer setup for training the lower-layer classifiers. To the best of our knowledge, this is the first error back-propagation method for a logic reasoning system.